Messaging System with Avatar Generation

1. A machine-implemented method of transmitting a message, comprising before training a neural network, receiving paired sets each comprising a self-image and a user-generated avatar linked to that self-image; forming a dataset comprising the received paired sets; training the neural network with the dataset to predict multiple trait values for a first static avatar based on a first input facial image, the neural network having a fanout of a top classification layer; receiving the first facial input image; generating the first static avatar with the trained neural network based on the first facial image using multiple trait values generated for the first static avatar; and sending a message with the generated static avatar, the generated static avatar identifying a sender of the message.

2. The method of claim 1 , wherein the generating the first static avatar is further based on subtraits.

3. The method of claim 1 , wherein the training further comprises balancing of the dataset to train the neural network independently across multiple trait values.

4. The method of claim 3 , wherein the balancing comprises applying a weight multiplier for each trait value, and the weight multiplier is based on an inverse square root of a probability of a given trait value.

5. The method of claim 1 , wherein the training further comprises filtering the dataset to train the neural network across multiple traits.

6. The method of claim 5 , wherein the filtering includes removing avatars from the dataset that include a default value for a trait.

7. The method of claim 6 , wherein default, values for a trait include skin tone, hair style, and pupil tone.

8. The method of claim 5 , wherein the filtering is performed independently for each trait.

9. The method of claim 5 , wherein the filtering removes blacklisted traits.

10. A machine-readable storage device embodying instructions that, when executed by a machine, cause the machine to perform operations comprising: before training a neural network, receiving paired sets each comprising a self-image and a user-generated avatar linked to that self-image; forming a dataset comprising the received pair sets; training the neural network with the dataset to predict multiple trait values for a first static avatar based on a first input facial image, the neural network having a fanout of a top classification layer; receiving the first facial input image; generating the first static avatar with the trained neural network based on the first image using multiple trait values generated for the first static avatar; and sending a message with the generated static avatar, the generated static avatar identifying a sender of the message.

11. A system, comprising: one or more processors of a machine; and a memory storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising: before training a neural network, receiving paired sets each comprising a self-image and a user-generated avatar linked to that self-image; forming a dataset comprising the received pair sets; training the neural network with the dataset to predict multiple trait values for a first static avatar based on a first input facial image, the neural network having a fanout of a top classification layer; receiving the first facial input image; generating the first static avatar with the trained neural network based on the first facial image using multiple trait values generated for the first static avatar; and sending a message with the generated static avatar, the generated static avatar identifying a sender of the message.

12. The system of claim 11 , wherein the generating the first static avatar is further based on subtraits.

13. The system of claim 11 , wherein the training operation further comprises balancing of a dataset to train the neural network independently across multiple trait values.

14. The system of claim 13 , wherein the balancing comprises applying a weight multiplier for each trait value, and the weight multiplier is based on an inverse square root of a probability of a given trait value.

15. The system of claim 11 , wherein the training operation further comprises filtering a dataset to train the neural network across multiple traits.

16. The system of claim 15 , wherein the filtering includes removing avatars from the dataset that include a default value for a trait.

17. The system of claim 16 , wherein default values for a trait include skin tone, hair style, and pupil tone.

18. The system of claim 15 , wherein the filtering is performed independently for each trait.

19. The system of claim 15 , wherein the filtering removes blacklisted traits.

20. The system of claim 19 , wherein the message is an Ephemeral Message.